This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:

Loss: 0.4355
Wer: 0.4968

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5405	0.85	400	0.8115	0.8949
0.5355	1.7	800	0.6292	0.7331
0.405	2.56	1200	0.5805	0.6699
0.3261	3.41	1600	0.5308	0.6513
0.2496	4.26	2000	0.4755	0.5850
0.1878	5.11	2400	0.4926	0.5448
0.1342	5.96	2800	0.4355	0.4968

Framework versions

Transformers 4.32.1
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3

KatMarie/wav2vec2-large-xls-r-300m-eu

wav2vec2-large-xls-r-300m-eu

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

KatMarie/
wav2vec2-large-xls-r-300m-eu